Aspects of mapping tasks onto parallel processing systems

Author

Siegel, Howard Jay ; Armstrong, James ; Watson, Daniel ; Nation, Wayne ; Allemang, Mark

Author_Institution

Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA

fYear

1991

fDate

11-13 Sep 1991

Firstpage

84

Lastpage

89

Abstract

A discussion of how three algorithms can map onto parallel processing systems is presented. Issues addressed are single instruction multiple data (SIMD)/multiple instruction multiple data (MIMD) tradeoffs, mixed-mode parallelism, the impact of partitioning the system for subtask parallelism, the effect on execution time of increasing the number of processors used, and the advantages of a flexible interprocessor communications network

Keywords

parallel algorithms; MIMD; SIMD; execution time; interprocessor communications network; mapping tasks; mixed-mode parallelism; multiple instruction multiple data; parallel processing systems; partitioning; single instruction multiple data; subtask parallelism; Communication networks; Communication system control; Laboratories; Large-scale systems; Multiprocessor interconnection networks; Parallel machines; Parallel processing; Partitioning algorithms; Smoothing methods; Switches;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Software and Applications Conference, 1991. COMPSAC '91., Proceedings of the Fifteenth Annual International

Conference_Location

Tokyo

Print_ISBN

0-8186-2152-4

Type

conf

DOI

10.1109/CMPSAC.1991.170156

Filename

170156